statistics review 4 sample size calculations统计评估4样本大小的计算.pdfVIP

Available online /content/6/4/335 Review Statistics review 4: Sample size calculations Elise Whitley1 and Jonathan Ball2 1Lecturer in Medical Statistics, University of Bristol, Bristol, UK 2Lecturer in Intensive Care Medicine, St George’s Hospital Medical School, London, UK Correspondence: Editorial Office, Critical Care, editorial@ Published online: 10 May 2002 Critical Care 2002, 6:335-341 This article is online at /content/6/4/335 © 2002 BioMed Central Ltd (Print ISSN 1364-8535; Online ISSN 1466-609X) Abstract The present review introduces the notion of statistical power and the hazard of under-powered studies. The problem of how to calculate an ideal sample size is also discussed within the context of factors that affect power, and specific methods for the calculation of sample size are presented for two common scenarios, along with extensions to the simplest case. Keywords statistical power, sample size Previous reviews in this series introduced confidence inter- while the P value determines how likely it is that the observed vals and P values. Both of these have been shown to depend effect in the sample is due to chance. A related quantity is the strongly on the size of the study sample in question, with statistical power of the study. Put simply, this is the probabil- larger samples generally resulting in narrower confidence ity of correctly identifying a difference between the two intervals and smaller P values. The question of how large a groups in the study sample when one genuinely exists in the study should ideally be is therefo